Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1254376 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.8298. Min Act: -0.0000

Data Index: 203809 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7877. Min Act: -0.0000

Data Index: 137322 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7314. Min Act: -0.0000

Data Index: 736202 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7192. Min Act: -0.0000

Data Index: 153899 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7155. Min Act: -0.0000

Data Index: 15537 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.7184. Min Act: -0.0000

Data Index: 811631 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6651. Min Act: -0.0000

Data Index: 592110 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6649. Min Act: -0.0000

Data Index: 572127 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1226739 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1064939 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6640. Min Act: -0.0000

Data Index: 452263 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1247369 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1275186 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6326. Min Act: -0.0000

Data Index: 718662 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6455. Min Act: -0.0000

Data Index: 285024 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6419. Min Act: -0.0000

Data Index: 244221 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1244436 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6399. Min Act: -0.0000

Data Index: 989383 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.8324. Min Range: -0.8324

Max Act: 0.6062. Min Act: -0.0000

Data Index: 723258 (C4 (Web Text))

Max Activating Token Index: 710